Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation and common connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.10
    3:0.07
    4:0.28
    5:0.03
    6:0.14
    7:0.09
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     capacity
    -1.51
    stood
    -1.51
    itte
    -1.43
     rank
    -1.43
     capacities
    -1.34
     purposes
    -1.31
     nude
    -1.28
     similarity
    -1.27
    ?)
    -1.27
     SAP
    -1.27
    POSITIVE LOGITS
    �醒
    1.69
     exting
    1.61
     Debor
    1.58
     Zar
    1.54
    Sac
    1.52
     Conquer
    1.51
    Grant
    1.47
     Guth
    1.46
     Frie
    1.45
     tyr
    1.42
    Act Density 0.001%

    No Known Activations